Detection of Fingerprint Alterations Using Deep Convolutional Neural Networks

Abstract

Fingerprint alteration is a challenge that poses enormous security risks. As a result, many research efforts in the scientific community have attempted to address the issue. However, non-existence of publicly available datasets that contain obfuscation and distortion of fingerprints makes it difficult to identify the type of alteration and thus the study and development of mechanism to correct the alteration and correctly identify individuals. In this work we present the publicly available Coventry Fingerprints Dataset (CovFingDataset) with unique attributes such as: ten fingerprints for 611 different subjects, gender, hand and finger name for each image, among others. We also provide a total of 55,249 images with three levels of alteration for z-cut, obliteration and central rotation synthetic alterations, which are the most common types of obfuscation and distortion. Moreover, we propose a Convolutional Neural Network (CNN) to identify this type of alterations. The proposed CNN model achieves a classification accuracy rate of 98.55%. Results are also compared with a residual CNN model pre-trained on ImageNet which produces an accuracy of 99.88%.

Deep Learning Modalities for Biometric Alteration Detection in 5G Networks-Based Secure Smart Cities

“…As seen from the table, both techniques report acceptable levels with our model beaten to second place in terms of PPV for obliteration alteration while it comes out tops in terms of PPV for the central rotation and z-cut alterations. Furthermore, our proposed DLMs performs better than [20] in terms of detection accuracy for the central rotation alteration. These results indicate the ability of our proposed models to match established ones with superior performance recorded in terms of central rotation alteration.…”

“…As presented in earlier in Section III, our study proposes the use of two deep learning frameworks (i.e., CNN and a hybrid that combines ConvLSTM and CNN) for efficient detection of alterations to fingerprint of authorised users. Furthermore, the validation reported in this subsection employs fingerprint images obtained from three levels of alteration (i.e., obliteration, central rotation, and z-cut) as available in the SOCOFing dataset [19][20].…”

“…In [20], CNN and ResNet18 deep learning model were utilised for detection of fingerprint alteration, the CNN structure was made up of convolutional layers with 20 3 3, 40 3 3, 60 3 3, and 80 3 3 Kernels. Additionally, the convolutional layers were followed by two fully connected layers with 1000 and 100 hidden units, respectively.…”

“…In another model, ResNet18 pretrained model was used. [20] in terms of alteration detection accuracy and predictive positive values (PPV). As seen from the table, both techniques report acceptable levels with our model beaten to second place in terms of PPV for obliteration alteration while it comes out tops in terms of PPV for the central rotation and z-cut alterations.…”

Deep Learning Algorithms based Fingerprint Authentication: Systematic Literature Review

“…Sometimes a criminal can alter his fingerprint in an attempt to by-pass security systems. A study by [94] conducted a research towards detecting altered fingerprints. The paper presented a novel database called Coventry Fingerprints Dataset (CovFingDataset) and made it public.…”